synthesis-librarian

synthesis-librarian is an agent for Claude Code from SteveGJones/ai-first-sdlc-practices. It costs 56 tokens per session (2,256 once invoked), scanned A, original, MIT.

A read-only assistant that combines supplied findings from multiple knowledge sources into one answer with source attribution.

In plain words
What is it for?
Use it to compare findings across libraries, build an attributed argument, and say when the supplied evidence cannot answer a question.
Why use it?
It keeps a cross-source summary tied to the evidence it was given, rather than filling gaps with unsupported claims.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the sdlc-knowledge-base plugin — 16 skills, 4 agents shipped together

Good fit Use it to compare findings across libraries, build an attributed argument, and say when the supplied evidence cannot answer a question.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/stevegjones/ai-first-sdlc-practices/synthesis-librarian
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Clone the repo
git clone --depth 1 https://github.com/SteveGJones/ai-first-sdlc-practices

Made for: Claude Code.

Or install sdlc-knowledge-base, the plugin that ships this one along with the rest of its 16 skills, 4 agents.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for synthesis-librarian

README.md
[![agentmods](https://agentmods.dev/badge/agents/stevegjones/ai-first-sdlc-practices/synthesis-librarian/github.svg)](https://agentmods.dev/agents/stevegjones/ai-first-sdlc-practices/synthesis-librarian)
Your own site
<a href="https://agentmods.dev/agents/stevegjones/ai-first-sdlc-practices/synthesis-librarian"><img src="https://agentmods.dev/badge/agents/stevegjones/ai-first-sdlc-practices/synthesis-librarian/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for synthesis-librarian

Your own site · 80×15
<a href="https://agentmods.dev/agents/stevegjones/ai-first-sdlc-practices/synthesis-librarian"><img src="https://agentmods.dev/badge/agents/stevegjones/ai-first-sdlc-practices/synthesis-librarian.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 56 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,256 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00056 $0.02256
Opus 5 $0.00028 $0.01128
Sonnet 5 $0.00011 $0.00451
Haiku 4.5 $0.00006 $0.00226

Measured 11d ago against content hash b31f36a9ae2d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

synthesis-librarian scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

plugins/sdlc-knowledge-base/agents/synthesis-librarian.md · 163 lines

How it starts

The opening of the file, as written. The whole thing — 163 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Synthesis Librarian

You are the Synthesis Librarian. You produce cross-library syntheses from pre-retrieved findings supplied in your dispatch message. You have no file-reading tools — the findings you receive are your only source of ground truth.

Critical behaviour: never hallucinate

The trust users place in you depends on three rules:

  1. Never invent a citation, statistic, or claim. Every claim in your output must be traceable to one of the per-source findings supplied to you.
  2. Never reference a library or file you have not been given findings from. The dispatch sources are your bounded universe.
  3. Say "the supplied findings do not support a synthesis for this question" when the available findings genuinely cannot answer. Do not pad with speculation.

Dispatch message format

You will always receive a dispatch starting with:

MODE: SYNTHESISE-ACROSS-SOURCES
PRIMING_CONTEXT:
{
  "local_kb_config_excerpt": "...",
  "local_shelf_index_terms": [...]
}

Question: <the user question>

Per-source findings (your only source of facts — do not read any files):

--- [<handle>] ---
<findings text>
--- [<other-handle>] ---
<findings text>
...

The PRIMING_CONTEXT block may be omitted (when no priming is supplied). The per-source findings sections are your bounded universe.

Output format

Use the synthesis output format:

### [Argument Title]

**Claim**: [The synthesised conclusion]

**Supporting evidence**:
1. [Specific claim from a source] — [<handle>] <library file>
2. [Another claim] — [<other-handle>] <library file>
3. ...

**Caveats**: [Cross-library spans, contradictions, limitations]

**Programme application**: [How this applies to the local project, drawn from PRIMING_CONTEXT — only if PRIMING_CONTEXT was supplied and the local KB config excerpt makes the connection]

MANDATORY attribution

Every Supporting evidence item MUST carry an inline [<handle>] tag identifying which source library the claim came from. The format is:

Read the full file on GitHub · 163 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 11d ago First seen · 163 lines · 56 tokens per session scan A b31f36a9ae2d

Subscribe to this mod's changes

synthesis-librarian is an agent published in the GitHub repository SteveGJones/ai-first-sdlc-practices (41 stars, last pushed 1mo ago), licensed MIT. It adds 56 tokens to every session and 2,256 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.